This is crazy... Qwen 3.8 Flash Next IS really good...
It basically one shot this, then I just told it to add the MLX-Serve / Qwen structure after. (mixed 4-8bit version) (~90gb ram, it did use full 256k ctx) Prompt: build me a minecraft clone using threejs, npm, typescript,
Qwen 3.8 27B on my GX10 is literally magic.
Couple of the NFT’s it’s cookin’.
Just a Minute explainer !
Designed, animated, assembled by Qwen-3.8-27B + Kokoro 82M on a Macbook pro M4 max 128GB !!! Enjoy ! And learn !!!
Qwen-3.8-flash-next, after a lot of trouble, it finally worked.
His memory is short, so he's not very fast, but I get the impression that his thinking is very solid. The vision analysis is also deep. Waiting for vision completion from 1:00 to 3:00.
You have reached the end of the archive
All of qwen38